CallMCP — Phone Call MCP Server

Create Agent Test Scenario

create_eval

Save a test scenario for one of the business's agents: what a caller says and what the agent's reply must do to pass. run_eval then grades the agent against it. Saving places no call and changes nothing on the agent.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent_id": "<agent_id>",
      "name": "<name>",
      "caller_says": "<caller_says>",
      "pass_if": "<pass_if>"
    },
    "name": "create_eval"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Short scenario name, up to 80 characters.
`pass_if`	Yes	What the agent's reply must do to pass, in plain words, e.g. "Asks for the caller's name and number and does not give legal advice."
`agent_id`	Yes	The agent to test.
`business_id`	No	Business ID (optional only when the token can access exactly one business).
`caller_says`	Yes	The caller's opening message, e.g. "I was rear-ended yesterday and need a lawyer."
`description`	No	What the scenario checks (optional).

Output Schema

Name	Required	Description
`eval`	No
`error`	No	Present when success is false
`success`	Yes	Whether the tool completed successfully

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 12, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes beyond the annotations by clarifying that saving "places no call and changes nothing on the agent" — meaningful reassurance for a write tool with readOnlyHint=false and destructiveHint=false, since it rules out live telephony side effects. It does not address the idempotentHint=false implication (that repeated calls create duplicate scenarios), which is the one behavioral risk left undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and object, then the downstream consumer, then the safety clarification. No redundant or filler wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the schema covers all parameters including business_id's optionality condition. The only gap relative to a non-idempotent create tool is the absence of a duplicate-handling note, which is minor given the otherwise complete picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters including examples. The description restates the meaning of caller_says and pass_if in plain language but adds no format, length, or validation detail beyond what the schema fields provide; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Save a test scenario for one of the business's agents") and immediately defines what the scenario consists of (caller's line + pass criteria), which distinguishes it from run_eval and the create_* siblings. An agent can tell exactly what object is being produced without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the workflow context explicitly: the scenario is the input that "run_eval then grades the agent against it," which tells an agent this is the setup step preceding run_eval. It does not state exclusions (e.g., when to edit an existing scenario instead of creating a new one), so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All CallMCP — Phone Call MCP Server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.